Neural Models for Key Phrase Detection and Question Generation
This incremental work could help augment reading comprehension datasets for improving machine reading systems or educational applications.
The authors tackled question generation from documents by developing a two-stage neural model that first extracts key phrases as candidate answers, then uses them to condition a sequence-to-sequence question generator. Their key-phrase extraction model significantly outperformed entity-tagging and rule-based baselines, and the overall system generated fluent, answerable questions.
We propose a two-stage neural model to tackle question generation from documents. First, our model estimates the probability that word sequences in a document are ones that a human would pick when selecting candidate answers by training a neural key-phrase extractor on the answers in a question-answering corpus. Predicted key phrases then act as target answers and condition a sequence-to-sequence question-generation model with a copy mechanism. Empirically, our key-phrase extraction model significantly outperforms an entity-tagging baseline and existing rule-based approaches. We further demonstrate that our question generation system formulates fluent, answerable questions from key phrases. This two-stage system could be used to augment or generate reading comprehension datasets, which may be leveraged to improve machine reading systems or in educational settings.